A proposed Load forecasting strategy developed on smart electrical grid employing deep learning techniques

Smart electrical grids, which involve the application of intelligent information and communication technologies, are becoming the core ingredient in the ongoing modernization of the electricity delivery infrastructure. They enable the real-time monitoring and direction of network components, which has led to the emergence of new jobs and responsibilities including autonomous intelligent load forecasting. As it gives energy management intelligence, load forecasting is a crucial function for the operation and planning of the electrical system. Many works and studies have been made over the years to enhance smart grids, almost all of these works target the data collected in Fog computing to deal with as this data continues to be collected over time. This paper, proposes a new approach for load forecasting using fuzzy logic and deep learning. It begins by gathering the first phase's chosen features, preprocessing those features, tuning the model, and evaluating the performance model. Afterwards, the tuned model is prepared for usage in the prediction environment. The effectiveness of the novel load forecasting approach has been demonstrated by experimental findings. Additionally, recent state-of-the-art load forecasting systems have been compared to the suggested strategy. It is demonstrated that the proposed load forecasting technique, which introduces precise load estimates, has a positive impact on maximizing system reliability, resilience, and stability